OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

radv: stop using VM_ALWAYS_VALID on APUs

Browse Source 
It seems that VM_ALWAYS_VALID means that all BOs must fit in
memory (VRAM+GTT) for each submission. This is causing a lot of
troubles when the total allocated memory is greater than the
available memory, especially on APUs.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8779>
This commit is contained in:
Samuel Pitoiset
2021-02-02 22:01:47 +01:00
committed by Marge Bot
parent 6a3de3a31f
commit 6ac6e2fbfb
1 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/amd/vulkan/winsys/amdgpu/radv_amdgpu_bo.c
View File

@@ -507,7 +507,13 @@ radv_amdgpu_winsys_bo_create(struct radeon_winsys *_ws,
request.flags |= AMDGPU_GEM_CREATE_EXPLICIT_SYNC;
if (flags & RADEON_FLAG_NO_INTERPROCESS_SHARING &&
ws->info.has_local_buffers &&
(ws->use_local_bos || (flags & RADEON_FLAG_PREFER_LOCAL_BO))) {
(ws->use_local_bos ||
/* VM_ALWAYS_VALID means that all BOs must fit in memory (VRAM+GTT)
* for each submission. This is causing a lot of troubles when the
* total allocated memory is greater than the available memory,
* especially on APUs.
*/
(ws->info.has_dedicated_vram && (flags & RADEON_FLAG_PREFER_LOCAL_BO)))) {
bo->base.is_local = true;
request.flags |= AMDGPU_GEM_CREATE_VM_ALWAYS_VALID;
}